Coursera
  • Arts and Humanities

    Press the right arrow key to expand submenu

  • Business

    Press the right arrow key to expand submenu

  • Computer Science

    Press the right arrow key to expand submenu

  • Data Science

    Press the right arrow key to expand submenu

  • Information Technology

    Press the right arrow key to expand submenu

  • Health

    Press the right arrow key to expand submenu

  • Math and Logic

    Press the right arrow key to expand submenu

  • Personal Development
  • Physical Science and Engineering

    Press the right arrow key to expand submenu

  • Social Sciences

    Press the right arrow key to expand submenu

  • Language Learning

    Press the right arrow key to expand submenu

  • Degrees

    Press the right arrow key to expand submenu

  • Certificates

    Press the right arrow key to expand submenu


  • Explore all of Coursera
  • Browse
  • Top Courses
  • Profile
  • My Purchases
  • Get 50% Off
  • Settings
  • Updates
  • Accomplishments
  • Help Center
    Coursera
    1. Neural Networks and Deep Learning
    2. Week 1
    3. Introduction to deep learning
    PreviousNext
      • Completed
        Quiz: Introduction to deep learning
        10 questions
    QuizQuiz • 30 min30 minutes

    Introduction to deep learning

    Activity Completed
    Submit your assignment
    Due DateApr 12, 2:59 AM EDTApril 12, 2:59 AM EDT
    Attempts3 every 8 hours
    Activity Completed
    Receive grade
    To Pass80% or higher
    Grade
    100%
    We keep your highest score

    Confirm Navigation

    Are you sure you want to leave this page?
      

    Confirm Navigation

    Are you sure you want to leave this page?
      
    Introduction to deep learning
    Graded Quiz • 30 min

    Due Apr 12, 2:59 AM EDT

    Check
    Congratulations! You passed!
    To Pass 80% or higher
    Grade
    100%

    Introduction to deep learning

    Latest Submission Grade
    100%
    1.
    Question 1

    What does the analogy “AI is the new electricity” refer to?

    1 / 1 point
    Check
    Correct

    Yes. AI is transforming many fields from the car industry to agriculture to supply-chain...

    2.
    Question 2

    Which of these are reasons for Deep Learning recently taking off? (Check the three options that apply.)

    1 / 1 point
    Check
    Correct

    These were all examples discussed in lecture 3.

    Check
    Correct

    Yes! The development of hardware, perhaps especially GPU computing, has significantly improved deep learning algorithms' performance.

    Check
    Correct

    Yes! The digitalization of our society has played a huge role in this.

    3.
    Question 3

    Recall this diagram of iterating over different ML ideas. Which of the statements below are true? (Check all that apply.)

    IDEA->CODE->EXPERIMENT

    1 / 1 point
    Check
    Correct

    Yes, as discussed in Lecture 4.

    Check
    Correct

    Yes, as discussed in Lecture 4.

    Check
    Correct

    Yes. For example, we discussed how switching from sigmoid to ReLU activation functions allows faster training.

    4.
    Question 4

    When an experienced deep learning engineer works on a new problem, they can usually use insight from previous problems to train a good model on the first try, without needing to iterate multiple times through different models. True/False?

    1 / 1 point
    Check
    Correct

    Yes. Finding the characteristics of a model is key to have good performance. Although experience can help, it requires multiple iterations to build a good model.

    5.
    Question 5

    Which one of these plots represents a ReLU activation function?

    1 / 1 point
    Check
    Correct

    Correct! This is the ReLU activation function, the most used in neural networks.

    6.
    Question 6

    Images for cat recognition is an example of “structured” data, because it is represented as a structured array in a computer. True/False?

    1 / 1 point
    Check
    Correct

    Yes. Images for cat recognition is an example of “unstructured” data.

    7.
    Question 7

    A demographic dataset with statistics on different cities' population, GDP per capita, economic growth is an example of “unstructured” data because it contains data coming from different sources. True/False?

    1 / 1 point
    Check
    Correct

    A demographic dataset with statistics on different cities' population, GDP per capita, economic growth is an example of “structured” data by opposition to image, audio or text datasets.

    8.
    Question 8

    Why is an RNN (Recurrent Neural Network) used for machine translation, say translating English to French? (Check all that apply.)

    1 / 1 point
    Check
    Correct

    Yes. We can train it on many pairs of sentences x (English) and y (French).

    Check
    Correct

    Yes. An RNN can map from a sequence of english words to a sequence of french words.

    9.
    Question 9

    In this diagram which we hand-drew in lecture, what do the horizontal axis (x-axis) and vertical axis (y-axis) represent?

    1 / 1 point
    Check
    Correct
    10.
    Question 10

    Assuming the trends described in the previous question's figure are accurate (and hoping you got the axis labels right), which of the following are true? (Check all that apply.)

    1 / 1 point
    Check
    Correct

    Yes. Bringing more data to a model is almost always beneficial.

    Check
    Correct

    Yes. According to the trends in the figure above, big networks usually perform better than small networks.